中文
相关论文

相关论文: $\alpha$-Information-theoretic Privacy Watchdog an…

200 篇论文

Recent research in differential privacy demonstrated that (sub)sampling can amplify the level of protection. For example, for $\epsilon$-differential privacy and simple random sampling with sampling rate $r$, the actual privacy guarantee is…

应用统计 · 统计学 2022-02-22 Jingchen Hu , Joerg Drechsler , Hang J. Kim

Local Differential Privacy (LDP) protocols allow an aggregator to obtain population statistics about sensitive data of a userbase, while protecting the privacy of the individual users. To understand the tradeoff between aggregator utility…

密码学与安全 · 计算机科学 2019-10-18 Milan Lopuhaä-Zwakenberg , Boris Škorić , Ninghui Li

We study the problem of Stochastic Convex Optimization (SCO) under the constraint of local Label Differential Privacy (L-LDP). In this setting, the features are considered public, but the corresponding labels are sensitive and must be…

数据结构与算法 · 计算机科学 2026-05-12 Lynn Chua , Badih Ghazi , Ravi Kumar , Pasin Manurangsi , Ziteng Sun , Chiyuan Zhang

The increased use of differential privacy (DP) has allowed the sharing of large amounts of data while reducing the risk of disclosure of sensitive information at the individual level. However, the noise introduced by DP methods makes…

统计方法学 · 统计学 2026-04-29 Jordan Awan , Xi Chen , Roberto Molinari

We study approximation algorithms for Maximum Constraint Satisfaction Problems (Max-CSPs) under differential privacy (DP) where the constraints are considered sensitive data. Information-theoretically, we aim to classify the best…

数据结构与算法 · 计算机科学 2026-02-11 Prathamesh Dharangutte , Jingcheng Liu , Pasin Manurangsi , Akbar Rafiey , Phanu Vajanopath , Zongrui Zou

The shuffle model of Differential Privacy (DP) is an enhanced privacy protocol which introduces an intermediate trusted server between local users and a central data curator. It significantly amplifies the central DP guarantee by…

密码学与安全 · 计算机科学 2024-07-26 Yixuan Liu , Yuhan Liu , Li Xiong , Yujie Gu , Hong Chen

We study an information theoretic privacy mechanism design problem for two scenarios where the private data is either observable or hidden. In each scenario, we first consider bounded mutual information as privacy leakage criterion, then we…

信息论 · 计算机科学 2022-12-26 Amirreza Zamani , Tobias J. Oechtering , Mikael Skoglund

The privacy-utility tradeoff problem is formulated as determining the privacy mechanism (random mapping) that minimizes the mutual information (a metric for privacy leakage) between the private features of the original dataset and a…

信息论 · 计算机科学 2026-05-12 Kousha Kalantari , Oliver Kosut , Lalitha Sankar

With the rapid growth of digital platforms, there is increasing apprehension about how personal data is collected, stored, and used by various entities. These concerns arise from the increasing frequency of data breaches, cyber-attacks, and…

密码学与安全 · 计算机科学 2025-04-28 Christopher C. Zawacki , Eyad H. Abed

Data trading has been hindered by privacy concerns associated with user-owned data and the infinite reproducibility of data, making it challenging for data owners to retain exclusive rights over their data once it has been disclosed.…

计算机科学与博弈论 · 计算机科学 2023-05-12 Yi Yu , Shengyue Yao , Juanjuan Li , Fei-Yue Wang , Yilun Lin

In this work, fundamental limits and optimal mechanisms of privacy-preserving data release that aims to minimize the privacy leakage under utility constraints of a set of multiple tasks are investigated. While the private feature to be…

信息论 · 计算机科学 2024-09-04 Ta-Yuan Liu , I-Hsiang Wang

The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and…

密码学与安全 · 计算机科学 2024-07-30 Shaowei Wang , Yun Peng , Jin Li , Zikai Wen , Zhipeng Li , Shiyu Yu , Di Wang , Wei Yang

Privacy-protecting data analysis investigates statistical methods under privacy constraints. This is a rising challenge in modern statistics, as the achievement of confidentiality guarantees, which typically occurs through suitable…

统计理论 · 数学 2022-09-14 Emanuele Dolera , Stefano Favaro

Differential privacy (DP) is a mathematical privacy notion increasingly deployed across government and industry. With DP, privacy protections are probabilistic: they are bounded by the privacy budget parameter, $\epsilon$. Prior work in…

密码学与安全 · 计算机科学 2023-03-02 Priyanka Nanayakkara , Mary Anne Smart , Rachel Cummings , Gabriel Kaptchuk , Elissa Redmiles

A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantified using expected Hamming distortion maximized over the set…

信息论 · 计算机科学 2018-08-02 Kousha Kalantari , Lalitha Sankar , Anand Sarwate

We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition significantly…

机器学习 · 统计学 2016-05-10 Yu-Xiang Wang , Jing Lei , Stephen E. Fienberg

Differential privacy is widely adopted to provide provable privacy guarantees in data analysis. We consider the problem of combining public and private data (and, more generally, data with heterogeneous privacy needs) for estimating…

机器学习 · 计算机科学 2021-11-02 Cecilia Ferrando , Jennifer Gillenwater , Alex Kulesza

This paper establishes the equivalence between Local Differential Privacy (LDP) and a global limit on learning any knowledge specific to a queried object. However, an output from an LDP query is not necessarily required to provide exact…

密码学与安全 · 计算机科学 2025-05-01 Mingen Pan

In this paper we study the problem of estimating the unknown mean $\theta$ of a unit variance Gaussian distribution in a locally differentially private (LDP) way. In the high-privacy regime ($\epsilon\le 1$), we identify an optimal privacy…

统计理论 · 数学 2025-03-06 Nikita P. Kalinin , Lukas Steinberger

Differential Privacy protects individuals' data when statistical queries are published from aggregated databases: applying "obfuscating" mechanisms to the query results makes the released information less specific but, unavoidably, also…

密码学与安全 · 计算机科学 2021-07-27 Natasha Fernandes , Annabelle McIver , Carroll Morgan